Summer ☀️ read on Computo: a new publication on reservoir computing in R!
Reservoir computing is a machine learning approach that relies on mapping inputs to higher dimensional spaces through a non-linear dynamical system (the reservoir), for example using a deep recurrent neural network and training only its final layer.
In this new publication, Thomas Ferté and co-authors Kalidou Ba, Dan Dutartre, Pierrick Legrand, Vianney Jouhet, Rodolphe Thiébaut, Xavier Hinaut and Boris P. Hejblum present the reservoirnet package, which is the first implementation of reservoir computing in R (rather then the existing Python and Julia).
The article also serves as an introduction to reservoir computing and illustrates its usefulness as well as the usage of the package on several real-case applications, including forecasting the number of COVID-19 hospitalizations at Bordeaux University Hospital using public data (epidemiological statistics, weather data) and hospital-level data (hospitalizations, ICU admission, ambulance service and ER notes). On this example, the authors also show how the weights of the connection between the input and the output layers can be used to compute feature importances.
The paper and accompanying R code are available at https://doi.org/10.57750/arxn-6z34
reservoirnet is available at https://cran.r-project.org/package=reservoirnet
#machineLearning #reservoirComputing #Rstats #openScience #openSource #openAccess
Minimal Genetic Circuit for Cellular Anticipation
https://www.biorxiv.org/content/10.1101/2025.04.22.649979v1?rss=1
Circuit design in biology and machine learning. I. Random networks and dimensional reduction
https://arxiv.org/abs/2408.09604
Steven A. Frank
https://stevefrank.org/
https://en.wikipedia.org/wiki/Steven_Frank_(biologist)
https://en.wikipedia.org/wiki/Reservoir_computing
Biological circuit to anticipate trend
https://academic.oup.com/evlett/article/8/5/719/7697097
#SyntheticBiology #SyntheticCircuits #ReservoirComputing #EvolutionTheory #ML #DimensionReduction #biocomputing #SteveFrank
Living systems have evolved cognitive complexity to reduce environmental uncertainty, enabling them to predict and prepare for future conditions. Anticipation, distinct from simple prediction, involves active adaptation before an event occurs and is a key feature of both neural and non-neural biological agents. Recent work by Steven Frank proposed a minimal anticipatory mechanism based on the moving average convergence-divergence principle from financial markets. Here, we implement this principle using synthetic biology to design and evaluate minimal genetic circuits capable of anticipating environmental trends. Through deterministic and stochastic analyses, we demonstrate that these motifs achieve robust anticipatory responses under a wide range of conditions. Our findings suggest that simple genetic circuits could be naturally exploited by cells to prepare for future events, providing a foundation for engineering predictive biological systems. ### Competing Interest Statement The authors have declared no competing interest.
Die #DeutschePhysikalischeGesellschaft hat auf ihrer Frühjahrstagung der Sektion #KondensierteMaterie drei Physiker mit Forschungspreisen für ihre wissenschaftlichen Arbeiten an der #UniMainz ausgezeichnet.
🎉 Herzlichen Glückwunsch an Dr. Libor Šmejkal zum Walter-Schottky-Preis 2025, an Dr. Robin R. Neumann zum INNOMAG Dissertationspreis 2025 und Grischa Beneke zum INNOMAG Master-Preis 2025 👉 https://www.phmi.uni-mainz.de/auszeichnungen-auf-dem-gebiet-der-physik-der-kondensierten-materie-fuer-drei-jgu-physiker/
#simplicialcomplex + #Causality +#Reservoircomputing:
"Higher-order Granger reservoir computing: simultaneously achieving scalable complex structures inference and accurate dynamics prediction" https://www.nature.com/articles/s41467-024-46852-1
For reservoir computing, improving prediction accuracy while maintaining low computing complexity remains a challenge. Inspired by the Granger causality, Li et al. design a data-driven and model-free framework by integrating the inference process and the inferred results on high-order structures.
AlexCrimi
Computo
Victoria Stuart 🇨🇦 🏳️⚧️
Uni Mainz
Science News
idw_online